© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 5188
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and symbols, especially those using LaTeX formatting

    oai_token-act-pair · gemini-2.0-flash

    mathematical formulae

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    +#+#
    -0.42
    ंत्री
    -0.36
    Todo
    -0.36
    Unmarshal
    -0.36
    안
    -0.36
    ModelForm
    -0.35
     todo
    -0.35
     kaynağından
    -0.35
    <strong>
    -0.34
    ArgsConstructor
    -0.33
    POSITIVE LOGITS
    <bos>
    1.11
     }}"></
    0.74
    '},
    
    0.64
    "},
    
    0.63
    ")));
    
    0.60
    ']")
    0.59
    )");
    
    0.59
    >")
    0.59
     "'");
    0.59
    '));
    
    0.58
    Activations Density 2.174%

    No Known Activations